Title | LOW-RESOLUTION VISUAL RECOGNITION VIA DEEP FEATURE DISTILLATION |
Authors | Zhu, Mingjian Han, Kai Zhang, Chao Lin, Jinlong Wang, Yunhe |
Affiliation | Peking Univ, Sch EECS, Key Lab Machine Percept MOE, Beijing, Peoples R China Huawei Noahs Ark Lab, Hong Kong, Peoples R China Peking Univ, Sch Software & Microelect, Beijing, Peoples R China |
Keywords | Low-Resolution Recognition Deep Convolutional Networks Teacher-Student Paradigm |
Issue Date | 2019 |
Publisher | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Abstract | Here we study the low-resolution visual recognition problem. Conventional methods are usually trained on images with large ROIs (regions of interest), while the regions and insider images are often small and blur in real-world applications. Therefore, deep neural networks learned on high-resolution images cannot be directly used for recognizing low-resolution objects. To overcome this challenging problem, we propose to use the teacher-student learning paradigm for distilling useful feature information from a pre-trained deep model on high-resolution visual data. In practice, a distillation loss is used to seek the perceptual consistency of low-resolution images and high-resolution images. By simultaneously optimizing the recognition loss and distillation loss, we formulate a novel low-resolution recognition approach. Experiments conducted on benchmarks demonstrate that the proposed method is capable to learn well-performed models for recognizing low-resolution objects, which is superior to the state-of-the-art methods. |
URI | http://hdl.handle.net/20.500.11897/544349 |
ISSN | 1520-6149 |
Indexed | CPCI-S(ISTP) |
Appears in Collections: | 信息科学技术学院 机器感知与智能教育部重点实验室 软件与微电子学院 |